All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality

9 September 2021

Papers citing "All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality"

10 / 10 papers shown

Title
Do Large Language Models know who did what to whom? Joseph M. Denning Xiaohan Bryor Snefjella Idan A. Blank 50 0 0 23 Apr 2025
Outlier dimensions favor frequent tokens in language models Iuri Macocco Nora Graichen Gemma Boleda Marco Baroni 37 0 0 27 Mar 2025
Are formal and functional linguistic mechanisms dissociated in language models? Michael Hanna Sandro Pezzelle Yonatan Belinkov 36 0 0 14 Mar 2025
ReSi: A Comprehensive Benchmark for Representational Similarity Measures Max Klabunde Tassilo Wald Tobias Schumacher Klaus H. Maier-Hein Markus Strohmaier Adriana Iamnitchi AI4TS VLM 50 5 0 13 Mar 2025
Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations Yize Zhao Tina Behnia V. Vakilian Christos Thrampoulidis 45 7 0 20 Feb 2025
Geometric Signatures of Compositionality Across a Language Model's Lifetime Jin Hwa Lee Thomas Jiralerspong Lei Yu Yoshua Bengio Emily Cheng CoGe 72 0 0 02 Oct 2024
LEACE: Perfect linear concept erasure in closed form Nora Belrose David Schneider-Joseph Shauli Ravfogel Ryan Cotterell Edward Raff Stella Biderman KELM MU 28 102 0 06 Jun 2023
Similarity of Neural Network Models: A Survey of Functional and Representational Measures Max Klabunde Tobias Schumacher M. Strohmaier Florian Lemmerich 32 63 0 10 May 2023
Measuring the Mixing of Contextual Information in the Transformer Javier Ferrando Gerard I. Gállego Marta R. Costa-jussá 11 46 0 08 Mar 2022
Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses Aina Garí Soler Marianna Apidianaki MILM 184 67 0 29 Apr 2021